Authors' reply

BMJ 1996; 312 doi: https://doi.org/10.1136/bmj.312.7030.577c (Published 02 March 1996) Cite this as: BMJ 1996;312:577
  1. Michael A Lewis,
  2. Walter O Spitzer,
  3. Kenneth D Macrae
  1. Associate director Director Potsdam Institute of Pharmacoepidemiology and Technology Assessment, 14482 Potsdam, Germany
  2. Reader in medical statistics Charing Cross and Westminster Medical School, London W6 8RP

    EDITOR,—Peter Sasieni is correct in asserting that a randomised controlled clinical trial is stronger than an observational case-control study. When concerns exist about the safety of drugs that are already being marketed, however, randomised controlled trials are seldom feasible. Most issues of drug safety concern very small risks. In the case of venous thromboembolic disease, a rough estimate of the baseline population risk is one event in 10000 woman years. Given this annual incidence of 0.0001 in unexposed women, with a two tailed (alpha) of 0.05, a β …

    View Full Text

    Log in

    Log in through your institution


    * For online subscription